{"id":"https://openalex.org/W2075669045","doi":"https://doi.org/10.1109/icassp.2013.6639218","title":"Integrated automatic expression prediction and speech synthesis from text","display_name":"Integrated automatic expression prediction and speech synthesis from text","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2075669045","doi":"https://doi.org/10.1109/icassp.2013.6639218","mag":"2075669045"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070433127","display_name":"Langzhou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Langzhou Chen","raw_affiliation_strings":["Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Mark J.F. Gales","raw_affiliation_strings":["Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075928867","display_name":"Norbert Braunschweiler","orcid":"https://orcid.org/0000-0003-1388-440X"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Norbert Braunschweiler","raw_affiliation_strings":["Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":["Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7977","last_page":"7981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8330271244049072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7285035252571106},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.7257272005081177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6026091575622559},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5838655233383179},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4936560094356537},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4920162856578827},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.44215306639671326},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.43545767664909363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350045323371887},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09896478056907654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06332361698150635}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8330271244049072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285035252571106},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.7257272005081177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6026091575622559},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5838655233383179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4936560094356537},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4920162856578827},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.44215306639671326},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43545767664909363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350045323371887},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09896478056907654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06332361698150635},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:623203","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/623203/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W80543058","https://openalex.org/W170974841","https://openalex.org/W2009417200","https://openalex.org/W2025638820","https://openalex.org/W2079521622","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2091430793","https://openalex.org/W2105468141","https://openalex.org/W2125552374","https://openalex.org/W2129142580","https://openalex.org/W2147760966","https://openalex.org/W2153914468","https://openalex.org/W2156146072","https://openalex.org/W2159290663","https://openalex.org/W2168980558","https://openalex.org/W2250525668","https://openalex.org/W2283817422","https://openalex.org/W2294232014","https://openalex.org/W2404480901","https://openalex.org/W3142087749","https://openalex.org/W6600088033","https://openalex.org/W6603264027","https://openalex.org/W6681813711","https://openalex.org/W6691572672","https://openalex.org/W6713894373"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2392243736","https://openalex.org/W2888483922","https://openalex.org/W86652014","https://openalex.org/W4396737233","https://openalex.org/W2367747139","https://openalex.org/W2334129531","https://openalex.org/W2515097069","https://openalex.org/W4300049944"],"abstract_inverted_index":{"Getting":[0],"a":[1,14,41,78,85,126,145,151],"text":[2],"to":[3,8,74,100],"speech":[4,39,98,123],"synthesis":[5,60,88,148],"(TTS)":[6],"system":[7,24,107],"speak":[9],"lively":[10],"animated":[11],"stories":[12],"like":[13],"human":[15],"is":[16],"very":[17],"difficult.":[18],"To":[19],"generate":[20],"expressive":[21,32,59,68,87,122,147],"speech,":[22],"the":[23,38,58,66,94,102,105,109,116,132,142],"can":[25],"be":[26],"divided":[27],"into":[28],"2":[29],"parts:":[30],"predicting":[31],"information":[33],"from":[34],"text;":[35],"and":[36,62,90,97,129],"synthesizing":[37],"with":[40],"particular":[42],"expression.":[43],"Traditionally":[44],"these":[45],"blocks":[46],"have":[47],"been":[48],"studied":[49],"separately.":[50],"This":[51],"paper":[52],"proposes":[53],"an":[54],"integrated":[55],"approach,":[56,76],"sharing":[57],"space":[61,149],"training":[63,92,110],"data":[64],"across":[65],"two":[67],"components.":[69],"There":[70],"are":[71],"several":[72],"advantages":[73],"this":[75],"including":[77],"simplified":[79],"expression":[80,95,133],"labelling":[81],"process,":[82],"support":[83],"of":[84,93,104,144],"continuous":[86,146],"space,":[89],"joint":[91],"predictor":[96],"synthesiser":[99],"maximise":[101],"likelihood":[103],"TTS":[106,128],"given":[108],"data.":[111],"Synthesis":[112],"experiments":[113],"indicated":[114],"that":[115],"proposed":[117],"approach":[118],"generated":[119],"far":[120],"more":[121],"than":[124],"both":[125],"neutral":[127],"one":[130],"where":[131],"was":[134],"randomly":[135],"selected.":[136],"The":[137],"experimental":[138],"results":[139],"also":[140],"showed":[141],"advantage":[143],"over":[150],"discrete":[152],"space.":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}